CtrlK
BlogDocsLog inGet started
Tessl Logo

web-development

Use when users need to implement, integrate, debug, build, deploy, or validate a Web frontend after the product direction is already clear, especially for React, Vue, Vite, browser flows, or CloudBase Web integration.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is web-development in TencentCloudBase/CloudBase-AI-Toolkit

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, actionable engineering skill with excellent validation workflow discipline, held back by content duplication and references to local bundle files that are not actually shipped.

Suggestions

De-duplicate the SPA History-mode guidance and the 'do not use for UI design' rule so each appears once in its most relevant section, cutting token cost without losing signal.

Ship the referenced `frameworks.md` and `browser-testing.md` in a local `references/` directory, or convert their inline pointers to the standalone-fallback URLs consistently so no reference resolves to a missing file.

Consolidate the overlapping 'Activation Contract', 'When to use this skill', and 'How to use this skill' sections, which currently restate the same use/do-not-use boundaries multiple times.

DimensionReasoningScore

Conciseness

It is non-pedantic and prescriptive rather than explaining basics, but it pads the token budget with repeated material — the SPA History-mode gotcha appears twice (lines 57 and 186), 'do not use for UI design' recurs across three sections, and browser-validation guidance is restated several times.

2 / 3

Actionability

Provides concrete executable commands (`tsc --noEmit`, `npm run build`, `npm install @cloudbase/js-sdk`), copy-paste-ready MCP JSON calls, and an init code snippet, meeting the fully-executable score-3 anchor.

3 / 3

Workflow Clarity

Numbered 'How to use this skill' and 'Core workflow' sequences plus Engineering constitution §2 give explicit validation checkpoints (tsc, eslint, build, tests, agent-browser) with a fix→re-validate feedback loop.

3 / 3

Progressive Disclosure

References are clearly signaled (`-> frameworks.md`, `browser-testing.md`, protocol URLs), but no references/ bundle directory ships with the skill, so the local files the body points to are absent; standalone-fallback URLs only partially compensate, leaving the structure below the clean one-level-deep score-3 bar.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, well-constructed description that names concrete actions, includes a natural 'Use when...' trigger with relevant framework keywords, and is clearly distinguished from sibling design skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'implement, integrate, debug, build, deploy, or validate a Web frontend' — matching the score-3 anchor rather than a single domain/action at score 2.

3 / 3

Completeness

Explicitly answers both 'what' (the verb list) and 'when' via the 'Use when users need to...' clause, satisfying the score-3 anchor.

3 / 3

Trigger Term Quality

Covers natural terms users would say — 'React, Vue, Vite, browser flows, or CloudBase Web integration' — with good breadth including framework names users actually name.

3 / 3

Distinctiveness Conflict Risk

Scoped to Web frontend engineering execution 'after the product direction is already clear', carving a distinct niche from ui-design and unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
TencentCloudBase/CloudBase-AI-Toolkit
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.